Vehicle and radar device thereof, position correction method, system, apparatus, medium

Abstract

The application discloses a vehicle and a radar device, a position correction method, a system, equipment and a medium thereof, and relates to the field of vehicles. The connecting part and the moving part are matched, the laser radar is close to the rear axle when the vehicle box is lifted, so that the risk of interference or damage by splashed goods between the laser radar and the vehicle box is avoided, the laser radar is away from the rear axle when the vehicle box is lowered, so that the detection range is expanded, and the safety hidden danger caused by the existence of the detection blind area is avoided. The extension and retraction of the laser radar are mainly completed through the cooperation of the connecting part and the moving part, the structure is simple, the cost is low, and excessive maintenance is not required. In the case of protecting the safety of the laser radar itself and avoiding the interference with the lifting of the vehicle box, the sufficient detection of the environmental information of the rear of the vehicle by the laser radar is met, the safety during the whole operation process of the vehicle box is improved, the safety of the laser radar itself is ensured, and the accurate parking and obstacle avoidance requirements during the driving and reversing of the vehicle are further met.

Description

Technical Field

[0001] This invention relates to the field of vehicles, and in particular to a vehicle and its radar device, position correction method, system, equipment, and medium. Background Technology

[0002] Currently, autonomous driving systems rely on perception systems to detect environmental information around the vehicle and control the vehicle to perform driving maneuvers such as acceleration, deceleration, steering, and obstacle avoidance based on the perception results. Common sensors used for detecting environmental information include cameras, LiDAR, millimeter-wave radar, and ultrasonic radar. LiDAR, due to its good environmental adaptability and high detection accuracy, is currently the primary sensor used by the perception system in autonomous driving systems. Especially in autonomous dump vehicles used in the logistics and transportation industry, rear LiDAR installed near the rear axle typically provides environmental information behind the vehicle to meet the requirements for accurate parking and obstacle avoidance during driving and reversing. Millimeter-wave radar and ultrasonic radar are generally installed on the vehicle bumper, flush with the vehicle surface. Cameras and LiDAR are generally slightly higher than the vehicle surface to avoid the vehicle itself obstructing the sensor's detection range. However, the sensor installation position should not be too far from the vehicle surface to avoid affecting the vehicle's passability and to prevent damage from frequent collisions during actual operation. Meanwhile, dump trucks need to frequently lift the cargo box to load and unload goods. If the rear lidar is installed close to the rear axle of the vehicle, its detection field of view on the left and right sides may be partially blocked by the cargo box, forming a detection blind spot, which may cause certain safety hazards. Conversely, if the rear lidar is far away from the rear axle of the vehicle, there may be lifting interference with the cargo box or an increased risk of damage to the goods splashed by the lidar.

[0003] To address the blind spots caused by rear LiDAR installation close to the vehicle's rear axle, existing technologies reduce these blind spots by extending the LiDAR when the vehicle is loaded with cargo exceeding its width. However, this approach relies primarily on motor-driven extension and retraction, significantly increasing system costs and placing high demands on motor control precision and subsequent maintenance. To mitigate the damage risk associated with rear LiDAR being located far from the rear axle, existing technologies cover the entire LiDAR with a protective shield when the cargo box is raised, reducing damage from material splashes during unloading. However, this solution requires direct mounting of the rear LiDAR on the rear axle, impacting its lateral detection range and creating potential blind spots. Summary of the Invention

[0004] The purpose of this invention is to provide a vehicle and its radar device, position correction method, system, equipment, and medium. The extension and retraction of the lidar are mainly accomplished through the cooperation of connecting and moving parts, resulting in a simple structure, low cost, and minimal maintenance. While protecting the lidar's own equipment safety and avoiding obstruction of cargo box lifting, the invention also satisfies the lidar's requirement for sufficient detection of environmental information behind the vehicle, improving safety throughout the cargo box movement process, ensuring the lidar's own equipment safety, and further meeting the requirements for precise parking and obstacle avoidance during vehicle driving and reversing.

[0005] To address the aforementioned technical problems, the present invention provides a lidar device, comprising:

[0006] A movable component that can slide horizontally on the rear axle of a vehicle.

[0007] The lidar is mounted on the moving component;

[0008] A connecting component that connects the moving part and the vehicle cargo box is used to move the lidar closer to the rear axle of the vehicle by driving the moving part when the vehicle cargo box is raised; and to move the lidar away from the rear axle of the vehicle by driving the moving part when the vehicle cargo box is lowered.

[0009] Optionally, the moving component is a guide rail and / or a displacement stage.

[0010] Optionally, the connecting component is a connecting rod and / or a push rod.

[0011] To address the aforementioned technical problems, the present invention also provides a vehicle, including a vehicle cargo box, a vehicle rear axle, and a lidar device as described above, wherein the lidar device is connected to the vehicle cargo box and the vehicle rear axle respectively.

[0012] To address the aforementioned technical problems, the present invention also provides a lidar position correction method, applied to the vehicle described above, comprising:

[0013] With the vehicle cargo box currently in an unlifted state, the initial position of the lidar is obtained, and the first point cloud data of the vehicle cargo box is obtained using the lidar.

[0014] Control the vehicle cargo box to rise, and control the vehicle cargo box to return to its original position after the vehicle cargo box has been raised;

[0015] If a confirmation command indicating that the vehicle cargo box has been restored to its original position is received, the second point cloud data of the current vehicle cargo box is obtained using the lidar.

[0016] The current position of the lidar is determined based on the first point cloud data, the second point cloud data, and the initial position.

[0017] Optionally, determining the current position of the lidar based on the first point cloud data, the second point cloud data, and the initial position includes:

[0018] Determine several hypothetical pose changes of the second point cloud data relative to the first point cloud data;

[0019] Determine several optimal distances corresponding to the aforementioned assumed pose changes;

[0020] The smallest optimal distance and the corresponding pose change among the optimal distances are taken as the final pose change of the lidar.

[0021] The current position of the lidar is determined based on the final pose change and the initial position.

[0022] Optionally, the process of determining the optimal sum of distances corresponding to any assumed pose change includes:

[0023] Based on any of the assumed pose changes, the second point cloud data is mapped to the target coordinate system where the first point cloud data is located to obtain the corresponding target point cloud data;

[0024] The nearest point search algorithm is used to pair up each data point in the first point cloud data and the target point cloud data, and the sum of distances between each pair of points is calculated. The sum of distances between each pair of points is then used as the optimal sum of distances corresponding to any assumed pose change.

[0025] Optionally, obtaining the initial position of the lidar includes:

[0026] The initial position of the lidar is determined based on the current position calibration of the lidar relative to the vehicle;

[0027] Correspondingly, after determining the current position of the lidar based on the first point cloud data, the second point cloud data, and the initial position, the method further includes:

[0028] The position calibration of the lidar relative to the vehicle is updated based on the current position of the lidar.

[0029] To address the aforementioned technical problems, the present invention also provides a lidar position correction system, applied to the vehicle as described above, comprising:

[0030] The initial position determination unit is used to obtain the initial position of the lidar when the current vehicle cargo box is in an unlifted state, and to obtain the first point cloud data of the current vehicle cargo box using the lidar.

[0031] The lifting unit is used to control the lifting of the vehicle cargo box and, after the vehicle cargo box has been lifted, control the vehicle cargo box to return to its original position.

[0032] The cargo box position determination unit is used to acquire the second point cloud data of the current vehicle cargo box using the lidar if it receives a confirmation command that the vehicle cargo box has been restored to its original position.

[0033] The current position determination unit is used to determine the current position of the lidar based on the first point cloud data, the second point cloud data, and the initial position.

[0034] To address the aforementioned technical problems, the present invention also provides an electronic device, comprising:

[0035] Memory, used to store computer programs;

[0036] A processor for implementing the steps of the lidar position correction method as described above.

[0037] To address the aforementioned technical problems, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the lidar position correction method as described above.

[0038] This invention provides a lidar device, including a lidar, a moving component, and a connecting component. The connecting component cooperates with the moving component to adjust the position of the lidar according to the lifting of the vehicle's cargo box. When the cargo box is lifted, the lidar is moved closer to the rear axle to avoid the risk of lifting interference or damage from splashed cargo. When the cargo box is lowered and leveling, the lidar is moved away from the rear axle to expand the detection range and avoid safety hazards caused by blind spots. The extension and retraction of the lidar are mainly accomplished through the cooperation of the connecting component and the moving component, resulting in a simple structure, low cost, and minimal maintenance. While protecting the lidar itself and avoiding obstruction of cargo box lifting, the device satisfies the lidar's requirement for sufficient detection of environmental information behind the vehicle, improving safety throughout the cargo box's movement, ensuring the lidar's own equipment safety, and further meeting the requirements for precise parking and obstacle avoidance during vehicle driving and reversing.

[0039] The present invention also provides a vehicle, a lidar position correction method, a lidar position correction system, an electronic device, and a computer-readable storage medium, which have the same beneficial effects as the lidar device described above. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the prior art and embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 A schematic diagram of the structure of a lidar device provided by the present invention;

[0042] Figure 2 This is a schematic diagram of the structure of a lidar device in a raised state, provided by the present invention.

[0043] Figure 3 A schematic diagram of the structure of a vehicle provided by the present invention;

[0044] Figure 4 A flowchart illustrating a lidar position correction method provided by the present invention;

[0045] Figure 5 This is a schematic diagram of the structure of a lidar position correction system provided by the present invention;

[0046] Figure 6 This is a schematic diagram of the structure of an electronic device provided by the present invention. Detailed Implementation

[0047] The core of this invention is to provide a vehicle and its radar device, position correction method, system, equipment, and medium. The extension and retraction of the lidar are mainly accomplished through the cooperation of connecting and moving parts, resulting in a simple structure, low cost, and minimal maintenance. While protecting the lidar's own equipment safety and avoiding obstruction of cargo box lifting, the invention satisfies the lidar's requirement for sufficient detection of environmental information behind the vehicle, improving safety throughout the cargo box movement process, ensuring the lidar's own equipment safety, and further meeting the requirements for precise parking and obstacle avoidance during vehicle driving and reversing.

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] The lidar device provided by this invention is mainly applicable to the fields of autonomous driving and driverless vehicles, especially in driverless or autonomous vehicles. Lidar installed near the rear axle of a vehicle is typically called a rear lidar. Rear lidar can provide environmental information behind the vehicle to meet the requirements for precise parking and obstacle avoidance during driving and reversing. This invention provides a retractable lidar system and a self-calibration method for lidar position correction. Detailed implementation methods are described below.

[0050] Please refer to Figure 1 , Figure 1 This invention provides a schematic diagram of a lidar device; to solve the above-mentioned technical problems, this invention provides a lidar device, comprising:

[0051] A movable component 2 that can slide horizontally on the rear axle 1 of the vehicle;

[0052] The lidar 3 is mounted on the moving part 2;

[0053] The connecting component 4, which connects the moving component 2 and the vehicle cargo box 5, is used to move the lidar 3 toward the rear axle 1 of the vehicle by driving the moving component 2 when the vehicle cargo box 5 is raised; and to move the lidar 3 away from the rear axle 1 of the vehicle by driving the moving component 2 when the vehicle cargo box 5 is lowered.

[0054] Specifically, the moving part 2 is connected to the vehicle cargo box 5 via the connecting part 4. The connecting part 4 converts the rotation of the vehicle cargo box 5 during lifting and lowering into a force that drives the moving part 2. When the vehicle cargo box 5 is lifted, the connecting part 4 drives the moving part 2 to move closer to the rear axle 1 of the vehicle. At the same time, since the lidar 3 is mounted on the moving part 2, it also moves closer to the rear axle 1 of the vehicle, thus avoiding positional conflict between the vehicle cargo box 5 and the lidar 3 during the lifting process, and also avoiding damage to the lidar 3 caused by the cargo. When the vehicle cargo box 5 is lowered, that is, during the process of the vehicle cargo box 5 being leveled and gradually returning to its position, the connecting part 4 drives the moving part 2 to move away from the rear axle 1 of the vehicle. At the same time, the lidar 3 also moves away from the rear axle 1 of the vehicle, thus ensuring that the lidar 3 can detect the environmental conditions behind the vehicle before the vehicle cargo box 5 is lifted. Furthermore, since the lidar 3 is relatively far from the rear axle at this time, the influence of the vehicle cargo box 5 on the detection range of the lidar 3 can be avoided, ensuring the detection effect of the lidar 3.

[0055] It is understood that there are multiple options for the connection between the connecting component 4 and the vehicle cargo box 5, as well as between the connecting component 4 and the moving component 2. These can be achieved through hinged, plugged, or riveted connections, etc. This application does not impose any particular limitation on this. There are also multiple options for the fixing of the lidar 3 to the moving component 2 and the fixing of the moving component 2 to the rear axle 1 of the vehicle. These can be achieved through bolted connections, welding, or riveting, etc. This application does not impose any particular limitation on this.

[0056] It should be noted that this application does not make any special restrictions on the specific types and implementation methods of the moving part 2, the connecting part 4, and the lidar 3. The lidar 3 can be implemented by a sensor, such as a line laser or a depth camera. The moving part 2 and the connecting part 4 can be implemented by various types of guiding mechanisms.

[0057] As a specific embodiment, please refer to Figure 1 and Figure 2 , Figure 2 This is a schematic diagram of the structure of a lidar device in a lifted state provided by the present invention. The retractable rear lidar system for dump trucks provided in this application includes a guide member mounted on the rear axle 1 of the vehicle, which can move horizontally along the vehicle direction; a rear lidar 3 mounted at the end of the guide member, which can move horizontally along the vehicle direction along with the guide member; and push rods hinged to the vehicle cargo box 5 and the guide member, respectively. The guide member serves as a moving component 2, and the push rod serves as a connecting component 4. In some embodiments, a cargo box cover 12 connected to the vehicle cargo box 5 may also be added.

[0058] When the vehicle's cargo box 5 is laid down, as Figure 1As shown, the hinge point between the push rod and the vehicle cargo box 5 moves away from the ground, simultaneously causing the hinge point between the push rod and the guide to move away from the rear axle, thus extending the rear lidar 3. When the vehicle cargo box 5 is lifted, as... Figure 2 As shown, the hinge point between the push rod and the vehicle cargo box 5 moves towards the ground, and at the same time drives the hinge point between the push rod and the guide to move towards the rear axle 1 of the vehicle, thereby realizing the retraction of the rear lidar 3.

[0059] The lidar device designed in this invention is a telescopic rear lidar system applicable to dump trucks. During cargo box lifting, the lidar 3 can be moved towards the rear axle, keeping it away from the tipped-over cargo and reducing equipment damage caused by cargo splashing. When the cargo box returns to a level position, the lidar 3 automatically moves away from the rear axle, minimizing vehicle obstruction of its detection range and ensuring the safety of autonomous driving. The telescopic movement of the lidar 3 is directly driven by the cargo box lifting, requiring no other drive components, thus offering advantages such as simple structure, low cost, and convenient maintenance.

[0060] The lidar device provided by this invention retracts the rear lidar 3 during cargo box lifting, thereby reducing the possibility of damage to the rear lidar 3 due to splashing during cargo box lifting and unloading. After the cargo box is leveled, the rear lidar 3 extends, thereby reducing vehicle obstruction of the lidar 3's detection range.

[0061] This invention provides a lidar device, including a lidar 3, a moving component 2, and a connecting component 4. The connecting component 4 cooperates with the moving component 2 to adjust the position of the lidar 3 according to the lifting status of the vehicle cargo box 5. When the vehicle cargo box 5 is lifted, the lidar 3 is moved closer to the rear axle to avoid the risk of lifting interference or damage from splashed cargo. When the vehicle cargo box 5 is lowered and in the process of leveling, the lidar 3 is moved away from the rear axle to expand the detection range and avoid safety hazards caused by blind spots. The extension and retraction of the lidar 3 is mainly accomplished through the cooperation of the connecting component 4 and the moving component 2. The structure is simple, the cost is low, and it does not require much maintenance. While protecting the lidar 3 itself and avoiding obstruction of the cargo box lifting, the lidar 3 can fully detect environmental information behind the vehicle, improving the safety of the entire cargo box movement process, ensuring the safety of the lidar 3 itself, and further meeting the requirements for precise parking and obstacle avoidance during vehicle driving and reversing.

[0062] Based on the above embodiments, as an optional embodiment, the moving component 2 is a guide rail and / or a displacement stage.

[0063] It is easy to understand that there are multiple ways to implement the moving part 2. The guide rail and / or displacement stage can all achieve the horizontal movement process. Any one of them can be selected as the moving part 2 to drive the lidar 3 and realize the extension and retraction of the lidar 3.

[0064] Specifically, the guide rail and / or displacement stage can realize the function of the moving part 2, and the extension and retraction of the lidar 3 can be realized in different forms. These moving parts 2 do not require additional drive system control, have low cost, simple structure, and do not require complicated maintenance process in the later stage, which reduces the maintenance cost of lidar device, expands the application range of the entire lidar device, and is conducive to further promotion.

[0065] As an alternative embodiment, the connecting component 4 is a connecting rod and / or a push rod.

[0066] It is easy to understand that there are multiple ways to implement the connecting component 4. Linkage rods and / or push rods can all convert the rotation of the vehicle cargo box 5 into a force that drives the moving component 2. Any one of these can be selected as the connecting component 4 to drive the moving component 2 and realize the extension and retraction of the lidar 3.

[0067] Specifically, the connecting rod and / or the push rod can both realize the function of the connecting component 4, and the extension and retraction of the lidar 3 can be realized in different forms. These connecting components 4 are low in cost, simple in structure, and do not require complicated maintenance processes in the later stage, which reduces the maintenance cost of the lidar device, expands the application range of the entire lidar device, and is conducive to further promotion.

[0068] Please refer to Figure 3 , Figure 3 This is a schematic diagram of the structure of a vehicle provided by the present invention. To solve the above-mentioned technical problems, the present invention also provides a vehicle, including a vehicle cargo box 5, a vehicle rear axle 1, and a lidar device as described above, wherein the lidar device is connected to the vehicle cargo box 5 and the vehicle rear axle 1 respectively.

[0069] It is easy to understand that the lidar device is applied to vehicles, especially vehicles with autonomous driving systems. This application does not make any special restrictions on the specific type and structure of the vehicle; nor does it make any special restrictions on the implementation of the vehicle cargo box 5 and the vehicle rear axle 1.

[0070] For an introduction to the vehicle provided by this invention, please refer to the above-described embodiment of the lidar device; further details of this invention will not be repeated here.

[0071] Please refer to Figure 4 , Figure 4 This is a flowchart illustrating a lidar position correction method provided by the present invention. To solve the above-mentioned technical problems, the present invention also provides a lidar position correction method, applied to the aforementioned vehicle, comprising:

[0072] S11: When the cargo box 5 of the current vehicle is in an unlifted state, obtain the initial position of the lidar 3, and use the lidar 3 to obtain the first point cloud data of the cargo box 5 of the current vehicle.

[0073] Considering that the aforementioned lidar device may cause lidar 3 to fail to accurately reset to its previous initial position after extension and retraction, resulting in errors in the position or distance information obtained by the vehicle when detecting the surrounding environment based on lidar 3, a method for updating the position of lidar 3 has been added to the vehicle's control system.

[0074] It is easy to understand that the vehicle cargo box 5 returns to its original position after each lifting. Therefore, the position of the vehicle cargo box 5 before and after the LiDAR 3 extends or retracts is fixed, and the position change of the LiDAR 3 can be determined by using the position of the vehicle cargo box 5. Therefore, the initial position of the LiDAR 3 can be obtained when the vehicle cargo box 5 is not lifted, and the first point cloud data representing the position of the vehicle cargo box 5 detected by the LiDAR 3 at this time can be obtained. This application does not make any special restrictions on the specific process and implementation of the initial position of the LiDAR 3 and the first point cloud data. The position information can be represented by Euler angles, quaternions, or matrices.

[0075] S12: Control the vehicle cargo box 5 to lift, and control the vehicle cargo box 5 to return to its original position after the vehicle cargo box 5 has been lifted;

[0076] It is understandable that after obtaining the initial position of the lidar 3 and the first point cloud data of the vehicle cargo box 5, the vehicle can be lifted and subsequent unloading operations can be completed. After lifting, it is necessary to control the vehicle cargo box 5 to return to its original position. This application does not make any special restrictions on the control process and driving method of the vehicle cargo box 5.

[0077] S13: If a confirmation command is received that the vehicle cargo box 5 has been restored to its original position, the second point cloud data of the current vehicle cargo box 5 is obtained using the lidar 3.

[0078] It should be noted that the position of the vehicle cargo box 5 remains fixed during the two detection processes of the LiDAR. After the vehicle cargo box 5 has returned to its original position, the LiDAR 3 is used to determine the second point cloud data of the vehicle cargo box 5. At this time, the absolute position of the vehicle cargo box 5 is the same as the absolute position of the vehicle cargo box 5 before it was lifted. At this time, the position of the vehicle cargo box 5 relative to the LiDAR 3 represented by the first and second point cloud data may be slightly different. This difference is due to the positional change of the LiDAR 3 after its extension and retraction. There are various choices for the representation of the second and first point cloud data. This application does not impose any particular limitation here. It can be implemented using sets or matrices, etc.

[0079] S14: Determine the current position of LiDAR 3 based on the first point cloud data, the second point cloud data, and the initial position.

[0080] Specifically, since the absolute position of the vehicle cargo box 5 does not change before and after lifting, the difference between the first point cloud data and the second point cloud data can represent the positional change of the lidar 3 before and after extension. Therefore, the current position of the lidar 3 can be determined using the first point cloud data, the second point cloud data, and the initial position.

[0081] It is easy to understand that the execution entity of steps S11-S14 is the vehicle's control system. The vehicle's control system receives the information detected by the LiDAR 3 and uses the LiDAR 3's own position information to accurately locate the position of obstacles behind the vehicle, thereby accurately determining whether the vehicle can proceed with subsequent operations such as parking, unloading, or reversing. Therefore, the accuracy of the LiDAR 3's own position information also affects the accurate operation during vehicle movement, and the control system needs to correct the LiDAR 3's own position information. The process of determining and correcting the current position of the LiDAR 3 by the control system can be performed after the vehicle's cargo box 5 has been lifted multiple times, or it can be performed once after each lift of the vehicle's cargo box 5. The frequency of the control system's update and correction of the LiDAR 3's position is not specifically limited in this application and can be adjusted according to actual application requirements.

[0082] The lidar device provided by this invention can be combined with the lidar position correction method described above to correct the position of lidar 3 after each extension and retraction, thereby reducing the impact of lidar 3 displacement error or error caused by deformation of moving parts after long-term operation on the detection accuracy of lidar 3, and ensuring the environmental detection effect of autonomous driving. For the introduction of lidar device and vehicle, please refer to the above embodiment, which will not be repeated here.

[0083] As an optional embodiment, determining the current position of the lidar 3 based on the first point cloud data, the second point cloud data, and the initial position includes:

[0084] Determine several hypothetical pose changes of the second point cloud data relative to the first point cloud data;

[0085] Determine several optimal distances corresponding to several assumed pose changes;

[0086] The minimum optimal distance and the corresponding pose change are taken as the final pose change of LiDAR 3.

[0087] The current position of lidar 3 is determined based on the final pose change and the initial position.

[0088] Considering that the assumptions regarding several pose transformation quantities are made to accurately find the final pose change of LiDAR 3, the values ​​of the pose change quantities can be slightly modified using the optimal iteration method or other iterative methods. The corresponding optimal distance sums are calculated and recorded. After obtaining the optimal distance sum, it can be compared with the previously recorded optimal distance sums, and the smaller distance sum and its corresponding pose change are retained. This iterative method is repeated until the preset number of iterations is met or the optimal distance sum reaches the convergence condition. The final optimal distance sum and its corresponding pose change are recorded. At this point, the final optimal distance sum must be the minimum value among several optimal distance sums. The pose transformation quantity corresponding to the smallest optimal distance sum is taken as the final pose change of LiDAR 3. After obtaining the final pose change of LiDAR 3, its current position can be determined using its initial position. This application does not specifically limit the specific calculation process and iterative implementation method for obtaining the final pose change.

[0089] Specifically, the final pose change of LiDAR 3 is determined by summing several optimal distances corresponding to several assumed pose changes, thereby improving the accuracy of the final pose change of LiDAR 3 and ensuring the accuracy and reliability of the current position of LiDAR 3 obtained by using the initial position and the final pose change, thus ensuring the environmental detection effect of autonomous driving and further ensuring vehicle safety.

[0090] As an optional embodiment, the process of determining the optimal sum of distances corresponding to any assumed pose change includes:

[0091] Based on any assumed pose change, the second point cloud data is mapped to the target coordinate system where the first point cloud data is located to obtain the corresponding target point cloud data;

[0092] The nearest point search algorithm is used to pair up each data point in the first point cloud data and the target point cloud data, and the sum of distances between each pair of points is calculated. The sum of distances between each pair of points is then used as the optimal sum of distances corresponding to any assumed pose change.

[0093] Considering that the first and second point cloud data detected by LiDAR 3 are both obtained using LiDAR 3's own position as the position reference, and the position of LiDAR 3 has changed after scaling, the reference positions of the first and second point cloud data are different, meaning they are in different coordinate systems. Therefore, it is necessary to map the second point cloud data to the target coordinate system where the first point cloud data is located, that is, to convert the second point cloud data into target point cloud data with the same reference position as the first point cloud data. Then, the sum of the distances between point pairs in the first and target point cloud data can be used to evaluate whether the final pose change of LiDAR 3 meets the accuracy requirements. To assess the accuracy of the final pose change, the nearest point search algorithm is used to calculate the sum of the optimal distances between each pair of points in the first point cloud data and the target point cloud data. The minimum sum of optimal distances is obtained through multiple iterations of position transformation, and the pose change corresponding to this minimum sum of optimal distances is used as the final pose change of LiDAR 3. The nearest point search method ensures that the distance between point pairs is necessarily the distance between corresponding point pairs in the point cloud data. This minimum distance is definitely due to the position change of LiDAR 3, ensuring that the final pose change of LiDAR 3 is determined based on the distance between corresponding point pairs, thereby guaranteeing the accuracy and reliability of the final pose change of LiDAR 3.

[0094] Specifically, the optimal distance is determined by using the distance between the target point cloud data mapped from the second point cloud data and the point pairs in the first point cloud data, thereby obtaining several optimal distances corresponding to several assumed pose changes, so as to accurately determine the position of the lidar in the future.

[0095] As an optional embodiment, obtaining the initial position of the lidar 3 includes:

[0096] The initial position of LiDAR 3 is determined based on the current position calibration of LiDAR 3 relative to the vehicle;

[0097] Correspondingly, after determining the current position of LiDAR 3 based on the first point cloud data, the second point cloud data, and the initial position, the process also includes:

[0098] The position calibration of LiDAR 3 relative to the vehicle is updated based on the current position of LiDAR 3.

[0099] It is easy to understand that the position of the LiDAR 3 can be determined by the control system using the vehicle as a reference point. Furthermore, the control system calibrates the position information of the LiDAR 3 relative to the vehicle. Therefore, the initial position of the LiDAR 3 can be directly determined using the position calibration in the control system. After determining the current position of the LiDAR 3, it also needs to be recalibrated, updating the original position calibration in the control system based on the current position. This application does not impose any special limitations on the position calibration method or specific form of the LiDAR 3 within the control system.

[0100] The lidar position correction method provided in this application can be further used as a self-calibration method for lidar 3. The aforementioned lidar device combined with the self-calibration method of lidar 3 can complete the dynamic recalibration of lidar 3 after each extension and retraction. The automatic calibration process after extension and retraction of lidar 3 can ensure the detection accuracy of the sensor, i.e. lidar 3, improve the usability of the entire lidar system, ensure the environmental detection effect of autonomous driving, and further ensure vehicle safety.

[0101] As a specific embodiment, position information can be represented in matrix form. A self-calibration method for a retractable rear lidar 3 on a dump truck includes the following steps: If a command to lift the cargo box is received, the current cargo box state T0 and D0 are recorded before the cargo box begins to lift. T0 is the transformation matrix of the lidar 3 relative to the vehicle reference coordinates, i.e., the current calibration result of the rear lidar 3, which is also the initial position of the lidar 3. D0 is the first point cloud data of the cargo box measured by the rear lidar 3. After receiving a confirmation command that the cargo box has been lifted and returned to a horizontal position, the cargo box point cloud data D1 is obtained through the rear lidar 3. D1 and D0 are compared to obtain the relative pose transformation T of the lidar 3 after one retraction / extension. E This means obtaining the final pose change of the lidar 3.

[0102] The specific process of comparing D1 and D0 is as follows: Assuming that the pose of LiDAR 3 remains unchanged after one stretching operation, the final pose change of LiDAR 3 is represented by a matrix, i.e., P delta =[0,0,0,0,0,0] T Define the initial According to T E Transform D1 to the coordinate system of the point cloud before scaling. This also means converting D1 to the case where the pose of the lidar remains unchanged. The position information represented by D0 at this point is based on the same location, meaning the position information is in the same coordinate system; calculating D0 and... The minimum distance sum of the data points within the data, i.e. pi p represents the data points within D0. j express Data points within; through optimization methods or ICP (Iterative Closest Point) methods, by assuming different pose transformations T multiple times. E And obtain different pose transformations T E In the case of D0 and Find the minimum distance sum among the internal data points, and after multiple iterations, identify the minimum of the minimum distance sums corresponding to different pose transformations. Then, find the optimal pose transformation corresponding to the minimum minimum distance sum. Optimal pose transformation As the final pose change of LiDAR 3 after scaling, and utilizing the optimal The updated calibration results of LiDAR 3 relative to the vehicle are as follows: The updated position calibration results of LiDAR 3 are as follows:

[0103] Please refer to Figure 5 , Figure 5 This is a schematic diagram of a lidar position correction system provided by the present invention; to solve the above-mentioned technical problems, the present invention also provides a lidar position correction system, applied to the aforementioned vehicle, comprising:

[0104] The initial position determination unit 21 is used to obtain the initial position of the lidar 3 when the current vehicle cargo box 5 is in an unlifted state, and to obtain the first point cloud data of the current vehicle cargo box 5 using the lidar 3.

[0105] The lifting unit 22 is used to control the lifting of the vehicle cargo box 5 and to control the vehicle cargo box 5 to return to its original position after the vehicle cargo box 5 has been lifted.

[0106] The cargo box position determination unit 23 is used to obtain the second point cloud data of the current vehicle cargo box 5 using the lidar 3 if it receives a confirmation command that the vehicle cargo box 5 has been restored to its original position.

[0107] The current position determination unit 24 is used to determine the current position of the lidar 3 based on the first point cloud data, the second point cloud data and the initial position.

[0108] As an optional embodiment, the current position determination unit 24 includes:

[0109] An iterative unit is used to determine several hypothetical pose changes of the second point cloud data relative to the first point cloud data.

[0110] The optimal distance and determination unit is used to determine several optimal distances and sums corresponding to several assumed pose changes, respectively.

[0111] The final pose change determination unit is used to take the minimum optimal distance and the corresponding pose change as the final pose change of the lidar 3.

[0112] The current position determination subunit is used to determine the current position of the lidar 3 based on the final pose change and the initial position.

[0113] As an optional embodiment, the optimal distance and determination unit includes an optimal distance and determination subunit, which is used to determine the optimal distance and sum corresponding to any assumed pose change.

[0114] The optimal distance and the determination of the sub-unit include:

[0115] The mapping unit is used to map the second point cloud data to the target coordinate system where the first point cloud data is located based on any assumed pose change, so as to obtain the corresponding target point cloud data.

[0116] The nearest point search unit is used to pair up each data point in the first point cloud data and the target point cloud data using the nearest point search algorithm, calculate the sum of distances between each pair of points, and use the sum of distances between each pair of points as the optimal sum of distances corresponding to any assumed pose change.

[0117] As an optional embodiment, the initial position determination unit 21 includes:

[0118] The initial position calibration unit is used to determine the initial position of the lidar 3 based on the current position calibration of the lidar 3 relative to the vehicle;

[0119] Correspondingly, it also includes:

[0120] The calibration update unit is used to update the position calibration of LiDAR 3 relative to the vehicle based on the current position of LiDAR 3.

[0121] For an introduction to the lidar position correction system provided by this invention, please refer to the embodiments of the lidar position correction method described above. This invention will not be repeated here.

[0122] Please refer to Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided by the present invention. To solve the above-mentioned technical problems, the present invention also provides an electronic device, comprising:

[0123] Memory 31 is used to store computer programs;

[0124] Processor 32 is used to implement the steps of the lidar position correction method as described above.

[0125] The processor 32 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 32 may be implemented using at least one hardware form selected from ARM (Advanced RISC Machines), DSP (Digital Signal Processor), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 32 may also include a main processor and a coprocessor. The main processor, also known as the central processing unit, is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 32 may integrate a GPU (graphics processing unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 32 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0126] The memory 31 may include one or more computer-readable storage media, which may be non-transitory. The memory 31 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 31 is used to store at least the following computer program, which, after being loaded and executed by the processor 32, is capable of implementing the relevant steps of the lidar position correction method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 31 may also include an operating system and data, and the storage method may be temporary or permanent storage. The operating system may include Windows, Unix, Linux, etc. The data may include, but is not limited to, data related to the lidar position correction method.

[0127] In some embodiments, the electronic device may further include a display screen, input / output interfaces, communication interfaces, a power supply, and a communication bus.

[0128] It will be understood by those skilled in the art that Figure 6 The structures shown do not constitute a limitation on electronic devices and may include more or fewer components than those shown.

[0129] For an introduction to the electronic device provided by this invention, please refer to the above-described embodiment of the lidar position correction method; further details of this invention will not be repeated here.

[0130] To address the aforementioned technical problems, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the aforementioned lidar position correction method.

[0131] It is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of this application. Specifically, the computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, and portable hard drives, or any type of media or device suitable for storing instructions or data, etc., and this application does not make any special limitations here.

[0132] For an introduction to the computer-readable storage medium provided by the present invention, please refer to the embodiments of the lidar position correction method described above; the present invention will not be repeated here.

[0133] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0134] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0135] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0136] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for correcting the position of a lidar sensor, characterized in that, This invention relates to a vehicle, which includes a cargo box, a rear axle, and a lidar device. The lidar device is connected to both the cargo box and the rear axle. The lidar device includes: a horizontally slidable component mounted on the rear axle; the component can move horizontally along the vehicle direction to move the lidar horizontally along the same direction; the lidar is mounted on the component; and a connecting component connecting the component and the cargo box, used to move the lidar closer to the rear axle by moving the component when the cargo box is raised, and to move the lidar away from the rear axle by moving the component when the cargo box is lowered. The lidar position correction method includes: With the vehicle cargo box currently in an unlifted state, the initial position of the lidar is obtained, and the first point cloud data of the vehicle cargo box is obtained using the lidar. Control the vehicle cargo box to rise, and control the vehicle cargo box to return to its original position after the vehicle cargo box has been raised; If a confirmation command indicating that the vehicle cargo box has been restored to its original position is received, the second point cloud data of the current vehicle cargo box is obtained using the lidar. The current position of the lidar is determined based on the first point cloud data, the second point cloud data, and the initial position.

2. The lidar position correction method as described in claim 1, characterized in that, The moving component is a guide rail and / or a displacement stage.

3. The lidar position correction method as described in claim 1, characterized in that, The connecting component is a connecting rod and / or a top rod.

4. The lidar position correction method as described in claim 1, characterized in that, Determining the current position of the lidar based on the first point cloud data, the second point cloud data, and the initial position includes: Determine several hypothetical pose changes of the second point cloud data relative to the first point cloud data; Determine several optimal distances corresponding to the aforementioned assumed pose changes; The smallest optimal distance and the corresponding pose change among the optimal distances are taken as the final pose change of the lidar. The current position of the lidar is determined based on the final pose change and the initial position.

5. The lidar position correction method as described in claim 4, characterized in that, The process of determining the optimal sum of distances corresponding to any assumed pose change includes: Based on any of the assumed pose changes, the second point cloud data is mapped to the target coordinate system where the first point cloud data is located to obtain the corresponding target point cloud data; The nearest point search algorithm is used to pair up each data point in the first point cloud data and the target point cloud data, and the sum of distances between each pair of points is calculated. The sum of distances between each pair of points is then used as the optimal sum of distances corresponding to any assumed pose change.

6. The lidar position correction method as described in claim 1, characterized in that, The process of obtaining the initial position of the lidar includes: The initial position of the lidar is determined based on the current position calibration of the lidar relative to the vehicle; Correspondingly, after determining the current position of the lidar based on the first point cloud data, the second point cloud data, and the initial position, the method further includes: The position calibration of the lidar relative to the vehicle is updated based on the current position of the lidar.

7. A lidar position correction system, characterized in that, This system is applied to vehicles, including a cargo box, a rear axle, and a lidar device. The lidar device is connected to both the cargo box and the rear axle. The lidar device includes: a horizontally slidable component mounted on the rear axle; the component can move horizontally along the vehicle direction to move the lidar horizontally along the same direction; the lidar is mounted on the component; and a connecting component connecting the component and the cargo box, used to move the lidar closer to the rear axle by moving the component when the cargo box is raised, and to move the lidar away from the rear axle by moving the component when the cargo box is lowered. The lidar position correction system includes: The initial position determination unit is used to obtain the initial position of the lidar when the current vehicle cargo box is in an unlifted state, and to obtain the first point cloud data of the current vehicle cargo box using the lidar. The lifting unit is used to control the lifting of the vehicle cargo box and, after the vehicle cargo box has been lifted, control the vehicle cargo box to return to its original position. The cargo box position determination unit is used to acquire the second point cloud data of the current vehicle cargo box using the lidar if it receives a confirmation command that the vehicle cargo box has been restored to its original position. The current position determination unit is used to determine the current position of the lidar based on the first point cloud data, the second point cloud data, and the initial position.

8. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for implementing the steps of the lidar position correction method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the lidar position correction method as described in any one of claims 1 to 6.

Images